Common Resnet gives bad result.

[nttstar]

Hi authors, I have tried your network structure with sphere loss and it can give similar result which mentioned in your paper. However, when I switched to use common resnet-50 or resnet-101 I can just got LFW score at about 97.xx%. Did you ever tried any other network structures?

I thought that the problem was caused by small norm(fx) where fx is the 512-dim embedding. As the W is normalized to one in sphereface, fx*W will become very small if norm(fx) is small to affect the total loss value. According to this I tried two approaches:

1. Normalize fx to a larger value like 32,
2. Use Prelu everywhere and set wd of the bias var in last FC layer to 0 and also remove the last BN layer.

Neither of them can work. Do you have any idea or give some hints?

[wy1iu]

Maybe you can replace the ReLU with PReLU. It will very likely help.